INDEX

Explanations

genes or genetic-related terms

oai_token-act-pair · gpt-3.5-turbo

the preposition "in" used frequently throughout the text

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.3.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

CLASSIFIED

-0.90

HAEL

-0.76

NOW

-0.75

ById

-0.73

llor

-0.72

Exit

-0.68

 undone

-0.67

 FUCK

-0.66

 podium

-0.65

 showc

-0.65

POSITIVE LOGITS

effic

1.41

 vitro

1.37

 accordance

1.33

 conjunction

1.30

clusions

1.26

efficiency

1.23

activation

1.22

 vivo

1.22

organic

1.21

 situ

1.21

Activations Density 0.547%

genes or genetic-related terms

the preposition "in" used frequently throughout the text

No Comments

No Known Activations